© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92594
    Prev
    Next
    INDEX
    Explanations

    C/C++ includes and standard libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ἐ
    -0.86
     odb
    -0.81
    idex
    -0.79
     jakim
    -0.79
    }';
    -0.79
     perguntou
    -0.79
     Lakh
    -0.76
     néhány
    -0.76
    ರು
    -0.76
    ---|
    -0.76
    POSITIVE LOGITS
    loem
    0.95
    conio
    0.91
    ocuk
    0.85
     
    0.83
     нада
    0.78
     main
    0.76
     mitad
    0.75
    main
    0.72
     cono
    0.71
     sat
    0.70
    Activations Density 0.019%

    No Known Activations